6 citations · 8 across the 7 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.RO2024★ 1 cited
Robotic Control via Embodied Chain-of-Thought Reasoning
Michał Zawalski, William Chen, Karl Pertsch +3
A key limitation of learned robot control policies is their inability to generalize outside their training data. Recent works on vision-language-action models (VLAs) have shown tha…
cs.LG2024★ 6 cited
Vision-Language Models Provide Promptable Representations for Reinforcement Learning
William Chen, Oier Mees, Aviral Kumar +1
Humans can quickly learn new behaviors by leveraging background world knowledge. In contrast, agents trained with reinforcement learning (RL) typically learn behaviors from scratch…